{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T03:01:04Z","timestamp":1790910064282,"version":"4.1.0"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732539","type":"print"},{"value":"9783031732546","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73254-6_13","type":"book-chapter","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T02:22:56Z","timestamp":1732674176000},"page":"213-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Can OOD Object Detectors Learn from\u00a0Foundation Models?"],"prefix":"10.1007","author":[{"given":"Jiahui","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhen","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingxian","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"13_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.E.: Towards open set deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1563\u20131572 (2016)","DOI":"10.1109\/CVPR.2016.173"},{"issue":"4","key":"13_CR3","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1049\/ip-vis:19941330","volume":"141","author":"CM Bishop","year":"1994","unstructured":"Bishop, C.M.: Novelty detection and neural network validation. IEE Proc.-Vis. Image Sig. Process. 141(4), 217\u2013222 (1994)","journal-title":"IEE Proc.-Vis. Image Sig. Process."},{"key":"13_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems 33, pp. 1877\u20131901 (2020)"},{"key":"13_CR5","unstructured":"Chang, C., Liu, Z., Lyu, X., Qi, X.: What matters in detecting AI-generated videos like Sora? arXiv preprint arXiv:2406.19568 (2024)"},{"issue":"240","key":"13_CR6","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"13_CR7","unstructured":"Deepshikha, K., Yelleni, S.H., Srijith, P., Mohan, C.K.: Monte Carlo dropblock for modelling uncertainty in object detection. arXiv preprint arXiv:2108.03614 (2021)"},{"key":"13_CR8","unstructured":"Deng, W., et al.: Can 3D vision-language models truly understand natural language? arXiv preprint arXiv:2403.14760 (2024)"},{"key":"13_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Dhamija, A., Gunther, M., Ventura, J., Boult, T.: The overlooked elephant of object detection: open set. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1021\u20131030 (2020)","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"13_CR11","unstructured":"Du, X., Fang, Z., Diakonikolas, I., Li, Y.: How does unlabeled data provably help out-of-distribution detection? arXiv preprint arXiv:2402.03502 (2024)"},{"key":"13_CR12","unstructured":"Du, X., Gozum, G., Ming, Y., Li, Y.: SIREN: shaping representations for detecting out-of-distribution objects. In: Advances in Neural Information Processing Systems 35, pp. 20434\u201320449 (2022)"},{"key":"13_CR13","unstructured":"Du, X., Sun, Y., Zhu, J., Li, Y.: Dream the impossible: outlier imagination with diffusion models. In: Advances in Neural Information Processing Systems 36 (2024)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Du, X., Wang, X., Gozum, G., Li, Y.: Unknown-aware object detection: learning what you don\u2019t know from videos in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13678\u201313688 (2022)","DOI":"10.1109\/CVPR52688.2022.01331"},{"key":"13_CR15","unstructured":"Du, X., Wang, Z., Cai, M., Li, Y.: VOS: learning what you don\u2019t know by virtual outlier synthesis. arXiv preprint arXiv:2202.01197 (2022)"},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR17","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference on Learning Representations (2022)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, A., Narayan, S., Joseph, K., Khan, S., Khan, F.S., Shah, M.: OW-DETR: open-world detection transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9235\u20139244 (2022)","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"13_CR19","unstructured":"Hall, D., et al.: Probabilistic object detection: definition and evaluation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1031\u20131040 (2020)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR21","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574 (2022)"},{"key":"13_CR22","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: International Conference on Learning Representations (2017)"},{"key":"13_CR23","unstructured":"Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606 (2018)"},{"key":"13_CR24","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems 33, pp. 6840\u20136851 (2020)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Hsu, Y.C., Shen, Y., Jin, H., Kira, Z.: Generalized ODIN: detecting out-of-distribution image without learning from out-of-distribution data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10951\u201310960 (2020)","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"13_CR26","unstructured":"Huang, R., Geng, A., Li, Y.: On the importance of gradients for detecting distributional shifts in the wild. In: Advances in Neural Information Processing Systems 34, pp. 677\u2013689 (2021)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Joseph, K., Khan, S., Khan, F.S., Balasubramanian, V.N.: Towards open world object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5830\u20135840 (2021)","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"13_CR28","unstructured":"Katz-Samuels, J., Nakhleh, J.B., Nowak, R., Li, Y.: Training OOD detectors in their natural habitats. In: International Conference on Machine Learning, pp. 10848\u201310865. PMLR (2022)"},{"key":"13_CR29","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Kong, S., Ramanan, D.: OpenGAN: open-set recognition via open data generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 813\u2013822 (2021)","DOI":"10.1109\/ICCV48922.2021.00085"},{"issue":"7","key":"13_CR31","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR32","unstructured":"Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: International Conference on Learning Representations (2018)"},{"key":"13_CR33","unstructured":"Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"13_CR34","unstructured":"Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: International Conference on Learning Representations, ICLR 2018 (2018)"},{"key":"13_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Liu, J., Chang, C., Liu, J., Wu, X., Ma, L., Qi, X.: MarS3D: a plug-and-play motion-aware model for semantic segmentation on multi-scan 3D point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9372\u20139381 (2023)","DOI":"10.1109\/CVPR52729.2023.00904"},{"key":"13_CR37","unstructured":"Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Advances in Neural Information Processing Systems 33, pp. 21464\u201321475 (2020)"},{"key":"13_CR38","unstructured":"Liu, X., Yang, H., Ravichandran, A., Bhotika, R., Soatto, S.: Continual universal object detection. arXiv preprint arXiv:2002.05347 (2020)"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Miller, D., Dayoub, F., Milford, M., S\u00fcnderhauf, N.: Evaluating merging strategies for sampling-based uncertainty techniques in object detection. In: International Conference on Robotics and Automation (ICRA), pp. 2348\u20132354 (2019)","DOI":"10.1109\/ICRA.2019.8793821"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Miller, D., Nicholson, L., Dayoub, F., S\u00fcnderhauf, N.: Dropout sampling for robust object detection in open-set conditions. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 3243\u20133249 (2018)","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427\u2013436 (2015)","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Perez-Rua, J.M., Zhu, X., Hospedales, T.M., Xiang, T.: Incremental few-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13846\u201313855 (2020)","DOI":"10.1109\/CVPR42600.2020.01386"},{"key":"13_CR43","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"13_CR44","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"13_CR45","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1007\/s11263-020-01355-6","volume":"128","author":"S Rahman","year":"2020","unstructured":"Rahman, S., Khan, S.H., Porikli, F.: Zero-shot object detection: joint recognition and localization of novel concepts. Int. J. Comput. Vis. 128, 2979\u20132999 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR46","unstructured":"Ren, J., Fort, S., Liu, J., Roy, A.G., Padhy, S., Lakshminarayanan, B.: A simple fix to Mahalanobis distance for improving near-OOD detection. arXiv preprint arXiv:2106.09022 (2021)"},{"key":"13_CR47","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28 (2015)"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR49","unstructured":"Sastry, C.S., Oore, S.: Detecting out-of-distribution examples with gram matrices. In: International Conference on Machine Learning, pp. 8491\u20138501. PMLR (2020)"},{"key":"13_CR50","unstructured":"Sun, Y., Ming, Y., Zhu, X., Li, Y.: Out-of-distribution detection with deep nearest neighbors. In: International Conference on Machine Learning, pp. 20827\u201320840. PMLR (2022)"},{"key":"13_CR51","unstructured":"Tack, J., Mo, S., Jeong, J., Shin, J.: CSI: novelty detection via contrastive learning on distributionally shifted instances. In: Advances in Neural Information Processing Systems 33, pp. 11839\u201311852 (2020)"},{"key":"13_CR52","unstructured":"Tan, H., et al.: Data pruning via moving-one-sample-out. In: Advances in Neural Information Processing Systems (2023)"},{"key":"13_CR53","unstructured":"Tao, L., Du, X., Zhu, X., Li, Y.: Non-parametric outlier synthesis. arXiv preprint arXiv:2303.02966 (2023)"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Tian, Y., Fan, L., Chen, K., Katabi, D., Krishnan, D., Isola, P.: Learning vision from models rivals learning vision from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15887\u201315898 (2024)","DOI":"10.1109\/CVPR52733.2024.01504"},{"key":"13_CR55","unstructured":"Wang, H., Liu, W., Bocchieri, A., Li, Y.: Can multi-label classification networks know what they don\u2019t know? In: Advances in Neural Information Processing Systems 34, pp. 29074\u201329087 (2021)"},{"key":"13_CR56","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Robust object detection via instance-level temporal cycle confusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9143\u20139152 (2021)","DOI":"10.1109\/ICCV48922.2021.00901"},{"key":"13_CR57","unstructured":"Wen, X., Zhao, B., Chen, Y., Pang, J., Qi, X.: Generalization beyond data imbalance: a controlled study on CLIP for transferable insights. arXiv preprint arXiv:2405.21070 (2024)"},{"key":"13_CR58","doi-asserted-by":"crossref","unstructured":"Wilson, S., Fischer, T., Dayoub, F., Miller, D., S\u00fcnderhauf, N.: SAFE: sensitivity-aware features for out-of-distribution object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23565\u201323576 (2023)","DOI":"10.1109\/ICCV51070.2023.02154"},{"key":"13_CR59","doi-asserted-by":"crossref","unstructured":"Wu, A., Chen, D., Deng, C.: Deep feature deblurring diffusion for detecting out-of-distribution objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13381\u201313391 (2023)","DOI":"10.1109\/ICCV51070.2023.01231"},{"key":"13_CR60","doi-asserted-by":"crossref","unstructured":"Wu, A., Deng, C.: Discriminating known from unknown objects via structure-enhanced recurrent variational autoencoder. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23956\u201323965 (2023)","DOI":"10.1109\/CVPR52729.2023.02294"},{"key":"13_CR61","unstructured":"Wu, Q., Chen, Y., Yang, C., Yan, J.: Energy-based out-of-distribution detection for graph neural networks. arXiv preprint arXiv:2302.02914 (2023)"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Wu, S., Tan, H., Tian, Z., Chen, Y., Qi, X., Jia, J.: Saco loss: sample-wise affinity consistency for vision-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27358\u201327369 (2024)","DOI":"10.1109\/CVPR52733.2024.02583"},{"key":"13_CR63","unstructured":"Wu, X., et al.: CL-NeRF: continual learning of neural radiance fields for evolving scene representation. In: Advances in Neural Information Processing Systems 36 (2024)"},{"key":"13_CR64","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"13_CR65","unstructured":"Zheng, H., et al.: Out-of-distribution detection learning with unreliable out-of-distribution sources. In: Advances in Neural Information Processing Systems 36, pp. 72110\u201372123 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73254-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T03:07:10Z","timestamp":1732676830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73254-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"ISBN":["9783031732539","9783031732546"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73254-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"28 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}